Quality-related Fault Detection Method Based on Adapt Recursive MPLS

Partial least square (PLS) is a multivariate statistical analysis method which can distinguish the quality-related and quality-unrelated spaces. Modification of PLS (MPLS) is an improved algorithm for PLS. However, MPLS has the disadvantages of large amount of calculation in batch modeling and cannot overcome the dynamic disturbance in process monitoring. In order to solve this problem, we propose an adapt recursive modified latent structure (AR-MPLS) algorithm, which uses recursive structure to extend to the dynamic domain. Finally, we use the Tennessee-Eastman process to verify the effectiveness of the proposed algorithm in the dynamic domain.